An ensemble-based 3D residual network for the classification of Alzheimer's disease.

Alzheimer's disease (AD) is a common type of dementia, with mild cognitive impairment (MCI) being a key precursor. Early MCI diagnosis is crucial for slowing AD progression, but distinguishing MCI from normal controls (NC) is challenging due to subtle imaging differences. Furthermore, different...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaoli Yang, Jiayi Zhou, Chenchen Wang, Xiao Li, Jiawen Wang, Angchao Duan, Nuan Du
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0324520
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850221357704413184
author Xiaoli Yang
Jiayi Zhou
Chenchen Wang
Xiao Li
Jiawen Wang
Angchao Duan
Nuan Du
author_facet Xiaoli Yang
Jiayi Zhou
Chenchen Wang
Xiao Li
Jiawen Wang
Angchao Duan
Nuan Du
author_sort Xiaoli Yang
collection DOAJ
description Alzheimer's disease (AD) is a common type of dementia, with mild cognitive impairment (MCI) being a key precursor. Early MCI diagnosis is crucial for slowing AD progression, but distinguishing MCI from normal controls (NC) is challenging due to subtle imaging differences. Furthermore, differentiating early MCI (EMCI) from late MCI (LMCI) is also important for interventions. This study proposes a deep learning-based approach using a weighted probability-based ensemble method to integrate results from three-dimensional residual networks (3D ResNet). (1) This study employs 3D ResNet-18, 3D ResNet-34, and 3D ResNet-50 architectures with the Convolutional Block Attention Module (CBAM). The attention mechanism enhances performance by helping the model focus on pertinent information. Data augmentation techniques are applied to address limited data and improve accuracy. (2) To overcome the limitation of the individual convolutional neural network (CNN), an ensemble learning method is adopted. The method assigns weights to each 3D CNN model based on prediction accuracy and integrates them to obtain the final result. Our method achieves accuracy of 94.87%, 92.31%, 95.49%, and 95.97% for MCI vs. NC, MCI vs. AD, EMCI vs. LMCI, and NC vs. EMCI vs. LMCI vs. AD, respectively. The results demonstrate the effectiveness of our method for AD diagnosis.
format Article
id doaj-art-b2e4da1bec93406ea94569767da8ec8e
institution OA Journals
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-b2e4da1bec93406ea94569767da8ec8e2025-08-20T02:06:44ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01206e032452010.1371/journal.pone.0324520An ensemble-based 3D residual network for the classification of Alzheimer's disease.Xiaoli YangJiayi ZhouChenchen WangXiao LiJiawen WangAngchao DuanNuan DuAlzheimer's disease (AD) is a common type of dementia, with mild cognitive impairment (MCI) being a key precursor. Early MCI diagnosis is crucial for slowing AD progression, but distinguishing MCI from normal controls (NC) is challenging due to subtle imaging differences. Furthermore, differentiating early MCI (EMCI) from late MCI (LMCI) is also important for interventions. This study proposes a deep learning-based approach using a weighted probability-based ensemble method to integrate results from three-dimensional residual networks (3D ResNet). (1) This study employs 3D ResNet-18, 3D ResNet-34, and 3D ResNet-50 architectures with the Convolutional Block Attention Module (CBAM). The attention mechanism enhances performance by helping the model focus on pertinent information. Data augmentation techniques are applied to address limited data and improve accuracy. (2) To overcome the limitation of the individual convolutional neural network (CNN), an ensemble learning method is adopted. The method assigns weights to each 3D CNN model based on prediction accuracy and integrates them to obtain the final result. Our method achieves accuracy of 94.87%, 92.31%, 95.49%, and 95.97% for MCI vs. NC, MCI vs. AD, EMCI vs. LMCI, and NC vs. EMCI vs. LMCI vs. AD, respectively. The results demonstrate the effectiveness of our method for AD diagnosis.https://doi.org/10.1371/journal.pone.0324520
spellingShingle Xiaoli Yang
Jiayi Zhou
Chenchen Wang
Xiao Li
Jiawen Wang
Angchao Duan
Nuan Du
An ensemble-based 3D residual network for the classification of Alzheimer's disease.
PLoS ONE
title An ensemble-based 3D residual network for the classification of Alzheimer's disease.
title_full An ensemble-based 3D residual network for the classification of Alzheimer's disease.
title_fullStr An ensemble-based 3D residual network for the classification of Alzheimer's disease.
title_full_unstemmed An ensemble-based 3D residual network for the classification of Alzheimer's disease.
title_short An ensemble-based 3D residual network for the classification of Alzheimer's disease.
title_sort ensemble based 3d residual network for the classification of alzheimer s disease
url https://doi.org/10.1371/journal.pone.0324520
work_keys_str_mv AT xiaoliyang anensemblebased3dresidualnetworkfortheclassificationofalzheimersdisease
AT jiayizhou anensemblebased3dresidualnetworkfortheclassificationofalzheimersdisease
AT chenchenwang anensemblebased3dresidualnetworkfortheclassificationofalzheimersdisease
AT xiaoli anensemblebased3dresidualnetworkfortheclassificationofalzheimersdisease
AT jiawenwang anensemblebased3dresidualnetworkfortheclassificationofalzheimersdisease
AT angchaoduan anensemblebased3dresidualnetworkfortheclassificationofalzheimersdisease
AT nuandu anensemblebased3dresidualnetworkfortheclassificationofalzheimersdisease
AT xiaoliyang ensemblebased3dresidualnetworkfortheclassificationofalzheimersdisease
AT jiayizhou ensemblebased3dresidualnetworkfortheclassificationofalzheimersdisease
AT chenchenwang ensemblebased3dresidualnetworkfortheclassificationofalzheimersdisease
AT xiaoli ensemblebased3dresidualnetworkfortheclassificationofalzheimersdisease
AT jiawenwang ensemblebased3dresidualnetworkfortheclassificationofalzheimersdisease
AT angchaoduan ensemblebased3dresidualnetworkfortheclassificationofalzheimersdisease
AT nuandu ensemblebased3dresidualnetworkfortheclassificationofalzheimersdisease